Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to the use and development of concepts or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    use of ability or removal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.78
     protoimpl
    -0.61
     tartalomajánló
    -0.60
     lenker
    -0.58
     HasFactory
    -0.57
     <<<<<<<<<<<<<<
    -0.56
     ProtoMessage
    -0.55
     AssemblyCulture
    -0.54
     ComVisible
    -0.53
     ErrIntOverflow
    -0.52
    POSITIVE LOGITS
    Tempo
    0.42
    zig
    0.41
     itſelf
    0.40
     whoſe
    0.39
     tempo
    0.39
     documentary
    0.39
    currencies
    0.39
     conspiracy
    0.39
    cely
    0.38
     Mön
    0.38
    Act Density 0.137%

    No Known Activations